Prediction of College Students' Sports Performance Based on Improved BP Neural Network

Area of Science:

• Sports Science
• Artificial Intelligence
• Educational Technology

Background:

• Sports performance prediction is a growing area of interest in higher education.
• Existing prediction models often suffer from low accuracy and slow convergence.
• Developing comprehensive student quality is a key focus for universities.

Purpose of the Study:

• To propose an improved BP neural network model for college students' sports performance prediction.
• To address the limitations of existing models, specifically accuracy and convergence speed.
• To leverage cloud computing for efficient model implementation and execution.

Main Methods:

• Data preprocessing of student sports performance metrics.
• Training a BP neural network with optimized weights and thresholds using the DE algorithm.
• Implementing the prediction model on a cloud computing platform for accelerated performance.

Main Results:

• The improved BP neural network model demonstrates enhanced accuracy in sports performance prediction.
• The DE algorithm optimization leads to more reliable prediction outcomes.
• Cloud computing integration significantly speeds up the prediction process.

Conclusions:

• The proposed model offers a more accurate and efficient solution for predicting college students' sports performance.
• This advancement provides valuable data for optimizing sports training programs.
• The study highlights the potential of AI-driven approaches in sports science and education.